© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15682
    Prev
    Next
    INDEX
    Explanations

    terms related to medical syndromes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various medical syndromes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endar
    -0.80
    undai
    -0.77
    yright
    -0.74
    oted
    -0.72
    estamp
    -0.67
    staff
    -0.63
    nuts
    -0.63
    tesy
    -0.63
    bernatorial
    -0.62
    endars
    -0.62
    POSITIVE LOGITS
     Syndrome
    1.06
    ptoms
    0.93
     syndrome
    0.89
     Symptoms
    0.81
     epile
    0.78
     plag
    0.77
     Spectrum
    0.77
    rosis
    0.76
     Osc
    0.72
    Mania
    0.72
    Activations Density 0.008%

    No Known Activations